Intelligent EHRs: Predicting Procedure Codes From Diagnosis Codes
This addresses the cumbersome task for doctors of manually selecting from thousands of procedure codes, though it is an incremental improvement over existing methods.
The paper tackles the problem of automatically predicting procedure codes (CPTs) from diagnosis codes (ICDs) in Electronic Health Records to streamline insurance claims, achieving a recall of 90@3 with a deep learning model trained on 2.3 million claims.
In order to submit a claim to insurance companies, a doctor needs to code a patient encounter with both the diagnosis (ICDs) and procedures performed (CPTs) in an Electronic Health Record (EHR). Identifying and applying relevant procedures code is a cumbersome and time-consuming task as a doctor has to choose from around 13,000 procedure codes with no predefined one-to-one mapping. In this paper, we propose a state-of-the-art deep learning method for automatic and intelligent coding of procedures (CPTs) from the diagnosis codes (ICDs) entered by the doctor. Precisely, we cast the learning problem as a multi-label classification problem and use distributed representation to learn the input mapping of high-dimensional sparse ICDs codes. Our final model trained on 2.3 million claims is able to outperform existing rule-based probabilistic and association-rule mining based methods and has a recall of 90@3.